List the merchant’s Meta product catalogs

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already supply readOnlyHint=true and destructiveHint=false, and the description reinforces them with 'Read-only, 0 credits' rather than contradicting them. It adds rich behavioral context beyond the annotations: the empty-list-is-not-the-merchant interpretation, that unreadable portfolios are reported rather than dropped, and that catalog visibility depends on portfolio admin status. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded and the critical interpretation caveats earn their place, but the description carries several sentences of marketing explanation about how Advantage+ catalog ads work ('one campaign that shows each person the products they are most likely to buy...'). This is beyond what an agent needs to call the tool correctly. It is comprehensive but over-specified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the full burden of describing return values, and it does: id, name, product count, owning portfolio with numeric ID, the portfolios array, the note field, and the unreadable case. It also covers the key failure-mode interpretation (empty list means admin gap, not absent catalog). Nothing an agent needs to invoke and interpret this tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, so per the rubric the baseline is 4; there is nothing additional to document. The description instead clarifies what the response will contain (portfolios array, note, unreadable flag), which is appropriate semantics for a parameterless listing tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource and its exact return shape ('The PRODUCT CATALOGS this Meta login can advertise from — id, name, how many products each holds, and which business portfolio owns it'). It also disambiguates against several siblings by name: it is the source of businessId for create_meta_catalog and is distinct from list_meta_product_sets and list_meta_catalog_products. An agent could pick this tool correctly without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit workflow guidance: 'START HERE for any "advertise my products" ask, then list_meta_product_sets to pick what to advertise.' It also names the chaining partner (create_meta_catalog) that consumes this tool's businessId output, and explains why this entry point is the right one versus going to Business Manager. The when-to-use is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.